© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37747
    Prev
    Next
    INDEX
    Explanations

    request and response handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    તિ
    0.55
    міна
    0.55
    钠
    0.55
    عي
    0.55
     Buddhists
    0.53
    ΗΣ
    0.53
    ındadır
    0.53
    ύτε
    0.52
     περί
    0.52
    汛
    0.51
    POSITIVE LOGITS
    {
    0.83
    s
    0.73
    t
    0.71
    c
    0.71
    (
    0.68
     {
    0.63
    st
    0.63
    ch
    0.63
    data
    0.61
    ;
    0.61
    Activations Density 0.006%

    No Known Activations